Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review
The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/13/2/301 |
_version_ | 1797443681302609920 |
---|---|
author | Bruce Burnett Shang-Ming Zhou Sinead Brophy Phil Davies Paul Ellis Jonathan Kennedy Amrita Bandyopadhyay Michael Parker Ronan A. Lyons |
author_facet | Bruce Burnett Shang-Ming Zhou Sinead Brophy Phil Davies Paul Ellis Jonathan Kennedy Amrita Bandyopadhyay Michael Parker Ronan A. Lyons |
author_sort | Bruce Burnett |
collection | DOAJ |
description | The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare their performance with that found in previous reviews. A literature search of four databases was performed for colorectal cancer prediction and prognosis model publications that included at least one machine-learning model. A total of 14 publications were identified for inclusion in the scoping review. Data was extracted using an adapted CHARM checklist against which the models were benchmarked. The review found similar methodological problems with machine-learning models to that observed in systematic reviews for non-machine-learning models, although model performance was better. The inclusion of machine-learning models in systematic reviews is required, as they offer improved performance despite similar methodological omissions; however, to achieve this the methodological issues that affect many prediction models need to be addressed. |
first_indexed | 2024-03-09T13:01:32Z |
format | Article |
id | doaj.art-31a68e79bcf844b79b3350c5cf7906da |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-09T13:01:32Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-31a68e79bcf844b79b3350c5cf7906da2023-11-30T21:53:36ZengMDPI AGDiagnostics2075-44182023-01-0113230110.3390/diagnostics13020301Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A ReviewBruce Burnett0Shang-Ming Zhou1Sinead Brophy2Phil Davies3Paul Ellis4Jonathan Kennedy5Amrita Bandyopadhyay6Michael Parker7Ronan A. Lyons8Swansea University Medical School, Swansea SA2 8PP, UKFaculty of Health, University of Plymouth, Plymouth PL4 8AA, UKSwansea University Medical School, Swansea SA2 8PP, UKClinithink Ltd., Bridgend CF31 1LH, UKClinithink Ltd., Bridgend CF31 1LH, UKSwansea University Medical School, Swansea SA2 8PP, UKSwansea University Medical School, Swansea SA2 8PP, UKSwansea University Medical School, Swansea SA2 8PP, UKSwansea University Medical School, Swansea SA2 8PP, UKThe inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare their performance with that found in previous reviews. A literature search of four databases was performed for colorectal cancer prediction and prognosis model publications that included at least one machine-learning model. A total of 14 publications were identified for inclusion in the scoping review. Data was extracted using an adapted CHARM checklist against which the models were benchmarked. The review found similar methodological problems with machine-learning models to that observed in systematic reviews for non-machine-learning models, although model performance was better. The inclusion of machine-learning models in systematic reviews is required, as they offer improved performance despite similar methodological omissions; however, to achieve this the methodological issues that affect many prediction models need to be addressed.https://www.mdpi.com/2075-4418/13/2/301machine learningcolorectal cancerrisk predictionscoping review |
spellingShingle | Bruce Burnett Shang-Ming Zhou Sinead Brophy Phil Davies Paul Ellis Jonathan Kennedy Amrita Bandyopadhyay Michael Parker Ronan A. Lyons Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review Diagnostics machine learning colorectal cancer risk prediction scoping review |
title | Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review |
title_full | Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review |
title_fullStr | Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review |
title_full_unstemmed | Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review |
title_short | Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review |
title_sort | machine learning in colorectal cancer risk prediction from routinely collected data a review |
topic | machine learning colorectal cancer risk prediction scoping review |
url | https://www.mdpi.com/2075-4418/13/2/301 |
work_keys_str_mv | AT bruceburnett machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT shangmingzhou machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT sineadbrophy machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT phildavies machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT paulellis machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT jonathankennedy machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT amritabandyopadhyay machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT michaelparker machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview AT ronanalyons machinelearningincolorectalcancerriskpredictionfromroutinelycollecteddataareview |